FACTORS OF EMERGING INFECTIOUS DISEASE OUTBREAK PREDICTION USING BIG DATA ANALYTICS: A SYSTEMATIC LITERATURE REVIEW

Infectious disease is an illness that can be transmitted from an infected individual to another. During the pre-vaccine era, infectious disease epidemics caused major fatalities in the population. The invention of vaccines that have dramatically reduced fatalities caused by infectious disease, led to the establishment of Global Immunization Vision and Strategy initiative that aims at increasing national vaccination coverage around the world. However, the appearance of emerging infectious disease calls for an establishment of an early warning mechanisms that can predict the next outbreak. Mathematical and statistical model that has been used to predict infectious disease outbreak used single source datasets that is inadequate for public health policymaking. Literatures suggested using big data analytics to get a better and accurate model. Big data deals not only with structured data from electronic health records but also integrate unstructured data obtained from social medias and webpages. Thus, this paper aims at identifying the factors frequently used in studies on infectious disease outbreak prediction, focusing specifically on two common disease outbreak in southeast Asia: dengue fever and measles. A systematic literature review approach that search across four databases found 284 literatures, of which 10 literatures were selected in the final process. Based on the review, it seems that studies on measles outbreak employed only single source datasets of patient data retrieved from electronic health records. Further research on measles outbreak prediction should combine various types of big data to produce more accurate prediction results.